Update README.md

README.md

@@ -6,6 +6,12 @@ base_model:
 - Qwen/Qwen2.5-0.5B
 - openai/clip-vit-large-patch14-336
 ---
+
+# Note that this is a model library with errors. 
+# In subsequent learning, I found that my model only used one visual token, which was a fatal mistake that resulted in a decrease in the performance of the model. 
+# I will revise this model library and release a new model when I have time in the future.
+
+
 # Visual Language Model Based on Qwen and CLIP
 
 This is a visual language multimodal model built upon the Qwen series language models and the CLIP visual encoder. It has been trained for 10 epochs on the LLaVA pre-training dataset and nearly 800K examples (150K instruction fine-tuning and 665K instruction mixed fine-tuning). However, due to data size is larger than model,  so it can only perform simple question-answering tasks on images and currently supports only English question answering.